|
|
--- |
|
|
tags: |
|
|
- merge |
|
|
- mergekit |
|
|
- gemma3 |
|
|
- gemma3-4B |
|
|
- tactical-analysis |
|
|
- problem-solving |
|
|
- devops |
|
|
- tactical |
|
|
- conversational |
|
|
- code |
|
|
- uncensored |
|
|
- decensored |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- coder3101/gemma-3-4b-it-heretic |
|
|
- vanta-research/scout-4b |
|
|
- GetSoloTech/Gemma3-Code-Reasoning-4B |
|
|
library_name: transformers |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
Made using [mergekit-gui](https://huggingface.co/spaces/Steelskull/mergekit-gui). |
|
|
|
|
|
- `vanta-research/scout-4b` has an absolutely amazing personality and is good at *cooperative* problem solving (something I find most models are not good at). |
|
|
- `GetSoloTech/Gemma3-Code-Reasoning-4B` is a strong coder. |
|
|
- `coder3101/gemma-3-4b-it-heretic` as a base (I am a professional who understands that this model is a tool and that I am responsable for how I use it). I also feel like people don't talk enough about how [abliteration](https://github.com/p-e-w/heretic) reduces hallucinations when asking the bot difficult questions. |
|
|
|
|
|
The end result is hopefully useful for programming and {cyber,information}-security. |
|
|
|
|
|
--- |
|
|
## Quantizations courtesy of team mradermacher |
|
|
- GGUF: [GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CodeCenturion-GGUF) |
|
|
- iMatrix: [iMatrix-GGUF](https://huggingface.co/mradermacher/Gemma3-4B-CodeCenturion-i1-GGUF) |
|
|
--- |
|
|
|
|
|
```yaml |
|
|
name: Gemma3-4B-CodeCenturion |
|
|
base_model: coder3101/gemma-3-4b-it-heretic |
|
|
dtype: bfloat16 |
|
|
merge_method: model_stock |
|
|
models: |
|
|
- model: vanta-research/scout-4b |
|
|
- model: GetSoloTech/Gemma3-Code-Reasoning-4B |
|
|
tokenizer_source: coder3101/gemma-3-4b-it-heretic |
|
|
``` |
